AI Models

Seed 1.6

General-purpose model released by the ByteDance Seed team.

Seed 1.6 Flash

Ultra-fast multimodal deep thinking model by ByteDance Seed

Seed-2.0-Lite

Versatile, cost‑efficient enterprise workhorse that delivers strong multimodal…

Seed-2.0-Mini

Seed-2.0-mini targets latency-sensitive, high-concurrency and cost-sensitive scenarios

ByteDanceImage

Seedream 4.5

ByteDance's image model tuned for editing consistency — subject detail, lighting and colour hold up.

Seedance 1.5 Pro

Generates video and its soundtrack in one pass, from a 4.5B dual-branch diffusion transformer.

Seedance 2.0

Text-, image- and reference-to-video with first/last frame control; holds character and camera.

Seedance 2.0 Fast

Speed- and cost-tuned Seedance 2.0: the same video workflows, traded against maximum output quality.

UI-TARS 7B

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments

Seed-2.0-Code

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.

Seed 2.1 Turbo

Multimodal model from ByteDance Seed for coding and long-horizon agent…

ByteDanceImage

Seedream 5.0 Lite

Seedream 5.0 Lite is an image generation model from ByteDance Seed.

ByteDanceImage

Seedream 5.0 Pro

Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed.

Seedance 2.0 Mini

Video generation model from ByteDance.

OpenAI

125

OpenAISpeech

GPT Audio

The gpt-audio model is OpenAI's first generally available audio model.

OpenAISpeech

GPT Audio Mini

A cost-efficient version of GPT Audio.

GPT-5.6 Luna

Fast, cost-efficient model in OpenAI's GPT-5.6 series.

GPT-5.6 Luna Pro

Same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to…

GPT-5.6 Sol

Flagship model in OpenAI's GPT-5.6 series.

GPT-5.6 Sol Pro

Same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to…

GPT-5.6 Terra

Balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol…

GPT-5.6 Terra Pro

Same underlying model as GPT-5.6 Terra

GPT Latest

Always points at the newest OpenAI GPT release, so you track the family without changing model IDs.

GPT Mini Latest

This model always redirects to the latest model in the OpenAI GPT Mini family.

GPT-3.5 Turbo (older v0613)

GPT-3.5 Turbo is OpenAI's fastest model.

GPT-3.5 Turbo 16k

This model offers four times the context length of gpt-3.5-turbo

GPT-3.5 Turbo Instruct

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related…

GPT-4

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving…

GPT-4 (older v0314)

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens

GPT-4 Turbo (older v1106)

The latest GPT-4 Turbo model with vision capabilities.

GPT-4 Turbo

The latest GPT-4 Turbo model with vision capabilities.

GPT-4 Turbo Preview

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs

GPT-4.1

Flagship large language model optimized for advanced instruction following

GPT-4.1 Mini

Mid-sized model delivering performance competitive with GPT-4o at substantially…

GPT-4.1 Nano

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1…

GPT-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with…

GPT-4o (2024-05-13)

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with…

GPT-4o (2024-08-06)

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs

GPT-4o (2024-11-20)

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural

GPT-4o Audio

The gpt-4o-audio-preview model adds support for audio inputs as prompts.

GPT-4o-mini

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with…

GPT-4o-mini (2024-07-18)

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with…

GPT-4o-mini Search Preview

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions.

GPT-4o Mini Transcribe

OpenAI's smaller, cost-efficient speech-to-text model built on GPT-4o…

GPT-4o Mini TTS

OpenAI's cost-efficient text-to-speech model.

GPT-4o Search Preview

GPT-4o Search Previewis a specialized model for web search in Chat Completions.

GPT-4o Transcribe

Speech-to-text built on GPT-4o audio, billed per token when you want transparent token-level costs.

GPT-5

OpenAI’s most advanced model, offering major improvements in reasoning, code quality

GPT-5 Chat

Designed for advanced, natural, multimodal and context-aware conversations for…

GPT-5 Codex

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding…

GPT-5 Image

GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities.

GPT-5 Image Mini

GPT-5 Mini paired with GPT Image 1 Mini — cheaper natively multimodal text-and-image generation.

GPT-5 Mini

Compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

GPT-5 Nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools

GPT-5 Pro

OpenAI’s most advanced model, offering major improvements in reasoning, code quality

GPT-5.1

Latest frontier-grade model in the GPT-5 series, offering stronger general-purpose…

GPT-5.1 Chat

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family

GPT-5.1-Codex

Specialized version of GPT-5.1 optimized for software engineering and coding…

GPT-5.1-Codex-Max

OpenAI’s latest agentic coding model, designed for long-running

GPT-5.1-Codex-Mini

Smaller and faster version of GPT-5.1-Codex

GPT-5.2

Latest frontier-grade model in the GPT-5 series, offering stronger agentic and long…

GPT-5.2 Chat

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family

GPT-5.2-Codex

Upgraded version of GPT-5.1-Codex optimized for software engineering and…

GPT-5.2 Pro

OpenAI’s most advanced model, offering major improvements in agentic coding and…

GPT-5.3 Chat

Update to ChatGPT's most-used model that makes everyday conversations smoother

GPT-5.3-Codex

OpenAI’s most advanced agentic coding model, combining the frontier software…

GPT-5.4

OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

GPT-5.4 Image 2

GPT-5.4 paired with GPT Image 2, to move between reasoning, coding and image generation in one flow.

GPT-5.4 Mini

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster

GPT-5.4 Nano

Most lightweight and cost-efficient variant of the GPT-5.4 family

GPT-5.4 Pro

OpenAI's most advanced model, building on GPT-5.4's unified architecture with…

GPT-5.5

OpenAI's frontier model for hard professional work: stronger reasoning, 1M+ token context.

GPT-5.5 Pro

High-capability GPT-5.5 tier for deep reasoning on high-stakes work, with a 1M+ token context.

GPT Chat Latest

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the…

gpt-oss-120b

Open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI…

gpt-oss-120b (free)

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI…

gpt-oss-20b

Open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

gpt-oss-20b (free)

Free Apache 2.0 open-weight model from OpenAI: 21B MoE with 3.6B active parameters per pass.

gpt-oss-safeguard-20b

Safety reasoning model from OpenAI built upon gpt-oss-20b.

o1

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking…

o1-pro

The o1 series of models are trained with reinforcement learning to think before they answer and…

o3

o3 is a well-rounded and powerful model across domains.

o3 Deep Research

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex

o3 Mini

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks

o3 Mini High

OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a…

o3 Pro

The o-series of models are trained with reinforcement learning to think before they answer and…

o4 Mini

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast

o4 Mini Deep Research

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling…

o4 Mini High

OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.

OpenAIVideo

Sora 2 Pro

Production-quality video with physics-accurate motion, synced audio and state across shots.

Text Embedding 3 Large

text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english…

Text Embedding 3 Small

text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model.

Text Embedding Ada 002

text-embedding-ada-002 is OpenAI's legacy text embedding model.

Whisper 1

OpenAI's Whisper speech-to-text model.

Whisper Large V3

OpenAI's open-source automatic speech recognition model offering both audio…

Whisper Large V3 Turbo

Optimized version of OpenAI's Whisper Large V3 speech recognition…

GPT-3.5 Turbo (batch)

GPT-3.5 Turbo is OpenAI's fastest model.

GPT-4.1 (batch)

GPT-4.1 is a flagship large language model optimized for advanced instruction following

GPT-4.1 Mini (batch)

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially…

GPT-4.1 Nano (batch)

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1…

GPT-4 Turbo (batch)

The latest GPT-4 Turbo model with vision capabilities.

GPT-4o (batch)

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with…

GPT-4o-mini (batch)

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with…

GPT-5.1 (batch)

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose…

GPT-5.2 (batch)

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long…

GPT-5.2 Pro (batch)

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and…

GPT-5.4 (batch)

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

GPT-5.4 Mini (batch)

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster

GPT-5.4 Nano (batch)

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family

GPT-5.4 Pro (batch)

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with…

GPT-5.5 (batch)

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads

GPT-5.5 Pro (batch)

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on…

GPT-5.6 Luna (batch)

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

GPT-5.6 Luna Pro (batch)

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to…

GPT-5.6 Sol (batch)

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.

GPT-5.6 Sol Pro (batch)

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to…

GPT-5.6 Terra (batch)

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol…

GPT-5.6 Terra Pro (batch)

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra

GPT-5 (batch)

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality

GPT-5 Codex (batch)

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding…

GPT-5 Mini (batch)

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

GPT-5 Nano (batch)

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools

GPT-5 Pro (batch)

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality

GPT Image 1

OpenAI's GPT Image 1 generates and edits images via the dedicated Images API.

GPT Image 1 Mini

A cost-efficient variant of GPT Image 1 for high-quality image generation at reduced latency and…

GPT Image 2

OpenAI's latest image generation model.

GPT Transcribe

High-accuracy speech-to-text model from OpenAI.

o1 (batch)

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking…

o1-pro (batch)

The o1 series of models are trained with reinforcement learning to think before they answer and…

o3 (batch)

o3 is a well-rounded and powerful model across domains.

o3 Mini (batch)

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks

o3 Mini High (batch)

OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a…

o3 Pro (batch)

The o-series of models are trained with reinforcement learning to think before they answer and…

o4 Mini (batch)

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast

o4 Mini High (batch)

OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high.

Text Embedding 3 Large (batch)

text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english…

Text Embedding 3 Small (batch)

text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model.

Text Embedding Ada 002 (batch)

text-embedding-ada-002 is OpenAI's legacy text embedding model.

Google

GoogleSpeech

Lyria 3 Clip Preview

30 second duration clips are priced at $0.04 per clip.

GoogleSpeech

Lyria 3 Pro Preview

Full-length songs are priced at $0.08 per song.

Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.

Nano Banana 2 (Gemini 3.1 Flash Image)

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image…

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest

Gemini 3.5 Flash

Google's high-efficiency multimodal model, bringing near-Pro level coding and…

Gemini Flash Latest

Always points at the newest Gemini Flash release, so you track the family without changing IDs.

Gemini Pro Latest

Always points at the newest Gemini Pro release, so you track the family without changing model IDs.

GoogleTranscription

Chirp 3

Google's latest multilingual speech-to-text model.

Gemini 2.0 Flash

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to Gemini Flash…

Gemini 2.0 Flash Lite

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to Gemini…

Gemini 2.5 Flash

Google's state-of-the-art workhorse model, specifically designed for advanced…

Nano Banana (Gemini 2.5 Flash Image)

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available.

Gemini 2.5 Flash Lite

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family

Gemini 2.5 Flash Lite Preview 09-2025

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family

Gemini 2.5 Pro

Google’s state-of-the-art AI model designed for advanced reasoning, coding

Gemini 2.5 Pro Preview 06-05

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding

Gemini 2.5 Pro Preview 05-06

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding

Gemini 3 Flash Preview

High speed, high value thinking model designed for agentic workflows

Nano Banana Pro (Gemini 3 Pro Image Preview)

Google's most advanced image generation and editing model, grounded via Gemini 3 Pro.

Nano Banana 2 (Gemini 3.1 Flash Image Preview)

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image…

Gemini 3.1 Flash Lite

Google’s GA high-efficiency multimodal model optimized for low-latency

Gemini 3.1 Flash Lite Preview

Google's high-efficiency model optimized for high-volume use cases.

Gemini 3.1 Flash TTS Preview

Text-to-speech model from Google

Gemini 3.1 Pro Preview

Google’s frontier reasoning model, delivering enhanced software…

Gemini 3.1 Pro Preview Custom Tools

Variant of Gemini 3.1 Pro that improves tool selection…

Gemini Embedding 001

gemini-embedding-001 provides a unified cutting edge experience across domains, including science

Gemini Embedding 2 Preview

Google's first multimodal embedding model.

Gemma 2 27B

Gemma 2 27B by Google is an open model built from the same research and technology used to create…

Gemma 3 12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Gemma 3 4B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Gemma 3n 4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices

Gemma 4 26B A4B

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Gemma 4 26B A4B (free)

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Gemma 4 31B

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image…

Gemma 4 31B (free)

Free 30.7B dense multimodal model: text and image in, 256K context, switchable thinking mode.

GoogleVideo

Veo 3.1

1080p video from text or image prompts with natively synchronised audio, for final production cuts.

GoogleVideo

Veo 3.1 Fast

Mid-tier Veo: faster and cheaper than 3.1, still high-quality video with natively synced audio.

GoogleVideo

Veo 3.1 Lite

Cheapest Veo tier for high-volume work: 720p and 1080p video with audio, at under half Fast's cost.

Gemini 2.5 Flash (batch)

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced…

Gemini 2.5 Flash Lite (batch)

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family

Gemini 2.5 Pro (batch)

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding

Gemini 3.1 Flash Lite (batch)

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency

Gemini 3.1 Pro Preview (batch)

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software…

Gemini 3.5 Flash (batch)

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and…

Gemini 3.5 Flash Lite

High-efficiency model from Google with upgraded agentic capabilities.

Gemini 3.5 Flash Lite (batch)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.

Gemini 3.6 Flash

High-efficiency model from Google for coding, agentic workflows

Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows

Gemini 3.7 Flash

Multimodal model from Google for fast agentic workflows, coding

Gemini 3.7 Flash (batch)

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding

Gemini 3 Flash Preview (batch)

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows

Gemini Embedding 2

Google: Gemini Embedding 2 is available on Rewind.ai.

Z.ai

GLM 5.2

Large-scale reasoning model from Z.ai.

GLM 4 32B

Cost-effective foundation language model.

GLM 4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications.

GLM 4.5 Air

GLM-4.5-Air is the lightweight variant of our latest flagship model family

GLM 4.5 Air (free)

Lightweight free variant of GLM-4.5, purpose-built for agent workloads on a smaller budget.

GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications.

GLM 4.6

Successor to GLM-4.5, with a longer context window and stronger coding and reasoning.

GLM 4.6V

Multimodal model for visual understanding across images, documents and mixed media, to 128K.

GLM 4.7

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming…

GLM 4.7 Flash

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and…

GLM 5

Z.ai's flagship open-source model for complex systems design and long-horizon agent workflows.

GLM 5 Turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in…

GLM 5.1

GLM tuned for long-horizon coding: works continuously on a task rather than minute-level exchanges.

GLM 5V Turbo

Native multimodal agent model for vision-based coding, long-horizon planning, image or video.

GLM 5.2 (batch)

GLM 5.2 is a large-scale reasoning model from Z.ai.

GLM 5.2 (free)

GLM 5.2 is a large-scale reasoning model from Z.ai.

GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and…

GLM Latest

This model always redirects to the latest GLM model from Z.ai.

Anthropic

Claude Fable 5

Mythos-class model from Anthropic, built for autonomous knowledge work and…

Claude Opus 4.7 (Fast)

Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x…

Claude Opus 4.8

Anthropic's most capable generally available model in the Opus family.

Claude Opus 4.8 (Fast)

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing…

Claude Sonnet 5

Anthropic's most capable Sonnet-class model, with frontier performance across coding

Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Claude Haiku Latest

Always points at the newest Claude Haiku release, so you track the family without new IDs.

Claude Opus Latest

Always points at the newest Claude Opus release, so you track the family without changing model IDs.

Claude Sonnet Latest

Always points at the newest Claude Sonnet release, so you track the family without changing IDs.

Claude 3 Haiku

Anthropic's fastest and most compact model for near-instant responsiveness.

Claude 3.5 Haiku

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use.

Claude 3.7 Sonnet

Advanced large language model with improved reasoning

Claude 3.7 Sonnet (thinking)

Claude 3.7 Sonnet is an advanced large language model with improved reasoning

Claude Haiku 4.5

Anthropic’s fastest and most efficient model

Claude Opus 4

Benchmarked as the world’s best coding model, at time of release

Claude Opus 4.1

Updated version of Anthropic’s flagship model

Claude Opus 4.5

Anthropic’s frontier reasoning model optimized for complex software…

Claude Opus 4.6

Anthropic’s strongest model for coding and long-running professional tasks.

Claude Opus 4.6 (Fast)

Opus 4.6 with identical capabilities at higher output speed, billed at six times the standard rate.

Claude Opus 4.7

Next-generation Anthropic Opus, built for long-running asynchronous agents and heavy coding work.

Claude Sonnet 4

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7

Claude Sonnet 4.5

Anthropic’s most advanced Sonnet model to date

Claude Sonnet 4.6

Anthropic's most capable Sonnet: iterative development, codebase navigation and end-to-end projects.

Claude Fable 5 (batch)

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and…

Claude Haiku 4.5 (batch)

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model

Claude Opus 4.1 (batch)

Claude Opus 4.1 is an updated version of Anthropic’s flagship model

Claude Opus 4.5 (batch)

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software…

Claude Opus 4.6 (batch)

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.

Claude Opus 4.7 (batch)

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running

Claude Opus 4.8 (batch)

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.

Claude Opus 5

Anthropic’s flagship model for demanding reasoning, coding

Claude Opus 5 (batch)

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding

Claude Opus 5 (Fast)

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing…

Claude Sonnet 4.5 (batch)

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date

Claude Sonnet 4.6 (batch)

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across…

Claude Sonnet 5 (batch)

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding

Tencent

Hy3

295B-parameter Mixture-of-Experts model from Tencent (21B active

Hy3 (free)

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active

Hunyuan A13B Instruct

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by…

Hy3 preview

High-efficiency MoE for agentic production workloads, with reasoning set to off, low or high.

Hy3 preview (free)

Free MoE model for agentic workflows, with reasoning you can dial between off, low and high.

Hy-MT2-1.8B

Compact 1.8B-parameter translation model from Tencent.

Hy-MT2-30B-A3B

Tencent's flagship translation model in the Hy-MT2 family.

Hy-MT2-7B

7B-parameter translation model from Tencent.

DeepSeek

DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following…

DeepSeek V3 0324

685B mixture-of-experts model, the 0324 iteration of DeepSeek's flagship chat family.

DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters

R1

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open…

R1 0528

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1

R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct

R1 Distill Qwen 32B

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B

DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original…

DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with…

DeepSeek V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate…

DeepSeek V3.2 Speciale

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning…

DeepSeek V4 Flash

Efficiency-tuned 284B MoE with a 1M-token context, built for fast inference over long inputs.

DeepSeek V4 Pro

1.6T-parameter MoE with a 1M-token context, aimed at advanced reasoning and coding over huge inputs.

DeepSeek V4 Flash 0731

Sparse mixture-of-experts model from DeepSeek

DeepSeek V4 Flash Latest

This model always redirects to the latest model in the DeepSeek V4 Flash family.

DeepSeek V4 Flash Vision Exp

Experimental vision-enabled version of DeepSeek V4 Flash 0731…

DeepSeek V4 Pro 0813

Large-scale mixture-of-experts model from DeepSeek.

MiniMax

MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax.

MiniMaxVideo

Hailuo 2.3

Text- and image-to-video aimed at creative production, cinematic scenes and character animation.

MiniMax-01

Combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image…

MiniMax M1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and…

MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and…

MiniMax M2-her

Dialogue-first large language model built for immersive roleplay

MiniMax M2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding

MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

MiniMax M2.5 (free)

Free model trained across real digital working environments; builds on the coding strengths of M2.1.

MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous

MiniMaxVideo

H3

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax.

MiniMax M3 (batch)

MiniMax-M3 is a multimodal foundation model from MiniMax.

MiniMaxSpeech

Speech 2.8 HD

MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax.

MiniMaxSpeech

Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax.

xAI

Grok 4.5

SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Grok Build 0.1

XAI’s fast coding model trained specifically for agentic software engineering…

Grok Latest

This model always redirects to the latest Grok model from xAI.

Grok 3 Beta

Grok 3 is the latest model from xAI.

Grok 3 Mini

A lightweight model that thinks before responding.

Grok 3 Mini Beta

Grok 3 Mini is a lightweight, smaller thinking model.

Grok 4

XAI's latest reasoning model with a 256k context window.

Grok 4 Fast

XAI's latest multimodal model with SOTA cost-efficiency and a 2M token context…

Grok 4.1 Fast

XAI's best agentic tool calling model that shines in real-world use cases like…

Grok 4.20

Fast reasoning with agentic tool calling, the lowest hallucination rate and strict prompts.

Grok 4.20 Multi-Agent

Variant of xAI’s Grok 4.20 designed for collaborative

Grok 4.3

Reasoning model taking text and images, suited to agentic workflows and high factual accuracy.

Grok Code Fast 1

Speedy and economical reasoning model that excels at agentic coding.

xAIImage

Grok Imagine Image 2.0

Image generation and editing model from xAI.

Sourceful

Riverflow V2 Fast

Fastest Riverflow 2.0 tier, for production image work where latency matters more than peak quality.

Riverflow V2 Fast Preview

Fastest variant of Sourceful's Riverflow V2 preview lineup.

Riverflow V2 Max Preview

Most powerful variant of Sourceful's Riverflow V2 preview lineup.

Riverflow V2 Pro

Top Riverflow 2.0 tier for image generation and editing, when you need fine control and clean text.

Riverflow V2 Standard Preview

Standard variant of Sourceful's Riverflow V2 preview lineup.

Riverflow V2.5 Fast

Speed-optimized variant of Sourceful's Riverflow 2.5 lineup

Riverflow V2.5 Pro

Most powerful variant of Sourceful's Riverflow 2.5 lineup

Alibaba

AlibabaChat

Tongyi DeepResearch 30B A3B

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab

Wan 2.6

1080p 24fps video from text, images, reference video or audio, with native lip-sync and A/V timing.

Wan 2.7

Text-, image- and reference-to-video with first/last frame control; references steer the style.

HappyHorse 1.0

Video generation model from Alibaba.

Qwen

Qwen3.7 Max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.

Qwen3.7 Plus

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

Qwen2.5 72B Instruct

Qwen2.5 72B is the latest series of Qwen large language models.

Qwen2.5 7B Instruct

Qwen2.5 7B is the latest series of Qwen large language models.

Qwen2.5 Coder 32B Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as…

Qwen-Max

Qwen-Max, based on Qwen2.5, provides the best inference performance among Qwen models

Qwen-Plus

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced…

Qwen Plus 0728

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model…

Qwen Plus 0728 (thinking)

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model…

Qwen-Turbo

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost

Qwen VL Max

Visual understanding model with 7500 tokens context length.

Qwen VL Plus

Qwen's Enhanced Large Visual Language Model.

Qwen2.5 VL 72B Instruct

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish and insects.

Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series

Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen

Qwen3 235B A22B Instruct 2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language…

Qwen3 235B A22B Thinking 2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language…

Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series

Qwen3 30B A3B Instruct 2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen

Qwen3 30B A3B Thinking 2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for…

Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series

Qwen3 8B

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series

Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by…

Qwen3 Coder 30B A3B Instruct

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts…

Qwen3 Coder Flash

Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder…

Qwen3 Coder Next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local…

Qwen3 Coder Plus

Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B.

Qwen3 Coder 480B A35B (free)

Free 480B MoE coding model, optimised for function calling, tool use and long-context reasoning.

Qwen3 Embedding 4B

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family

Qwen3 Embedding 8B

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family

Qwen3 Max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in…

Qwen3 Max Thinking

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series

Qwen3 Next 80B A3B Instruct

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized…

Qwen3 Next 80B A3B Instruct (free)

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized…

Qwen3 Next 80B A3B Thinking

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs…

Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation…

Qwen3 VL 235B A22B Thinking

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual…

Qwen3 VL 30B A3B Instruct

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual…

Qwen3 VL 30B A3B Thinking

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual…

Qwen3 VL 32B Instruct

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for…

Qwen3 VL 8B Instruct

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series

Qwen3 VL 8B Thinking

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model

Qwen3.5-122B-A10B

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that…

Qwen3.5-27B

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism

Qwen3.5-35B-A3B

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture…

Qwen3.5 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that…

Qwen3.5-9B

Multimodal foundation model from the Qwen3.5 family

Qwen3.5-Flash

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates…

Qwen3.5 Plus 2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that…

Qwen3.5 Plus 2026-04-20

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba.

Qwen3.6 27B

Dense 27-billion-parameter language model from the Qwen Team at Alibaba

Qwen3.6 35B A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total…

Qwen3.6 Flash

Fast, efficient language model from Alibaba's Qwen 3.6 series.

Qwen3.6 Max Preview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse…

Qwen3.6 Plus

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse…

QwenSpeech

Qwen-Audio-3.0-TTS Flash

Alibaba's fast, cost-efficient text-to-speech model

QwenSpeech

Qwen-Audio-3.0-TTS Plus

Alibaba's higher-quality text-to-speech model

QwenImage

Qwen Image 3

Unified image generation and editing model from Qwen.

QwenImage

Qwen Image 3 Pro

Image generation and editing model from Qwen.

Qwen3.7 Flash

Vision-language reasoning model from Alibaba.

Qwen3.8 2.4T A95B

Open-weight sparse mixture-of-experts model from Qwen and the open-weight…

Qwen3.8 27B

Open-weight dense vision-language model from Qwen.

Qwen3.8 Max

Flagship model in Alibaba's Qwen3.8 series, the general-availability successor…

QwenTranscription

Qwen3 ASR 0.6B

Compact automatic speech recognition model from Qwen.

QwenTranscription

Qwen3 ASR 1.7B

Automatic speech recognition model from Qwen.

QwenTranscription

Qwen3 ASR Flash

Qwen3-ASR-Flash is Alibaba's automatic speech recognition service

Black Forest Labs

FLUX.2 Flex

FLUX.2 tier for complex text and typography, with multi-reference editing in one architecture.

FLUX.2 Klein 4B

Open-weights 4B FLUX.2: text-to-image with strong prompt adherence at the low end of the cost range.

FLUX.2 Max

Top-tier FLUX.2 image model, for when prompt understanding and editing consistency matter most.

FLUX.2 Pro

A high-end image generation and editing model focused on frontier-level visual quality and…

Black Forest LabsVideo

FLUX.3 Video

FLUX.3 Video is a video generation model from Black Forest Labs.

Black Forest LabsVideo

FLUX Video Upscale

FLUX Video Upscale is a video upscaling model from Black Forest Labs.

Xiaomi

MiMo-V2-Flash

Open-source foundation language model developed by Xiaomi.

MiMo-V2-Omni

Frontier omni-modal model that natively processes image

MiMo-V2-Pro

Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M…

MiMo-V2.5

Native omnimodal model at roughly half Pro's cost, stronger on image and video understanding.

MiMo-V2.5-Pro

Xiaomi's flagship for agentic work and complex software engineering across long-horizon tasks.

MoonshotAI

Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family

Kimi K3

2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

Kimi Latest

Always points at the newest MoonshotAI Kimi release, so you track the family without changing IDs.

Kimi K2 0711

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot…

Kimi K2 0905

September update of Kimi K2 0711.

Kimi K2 Thinking

Moonshot AI’s most advanced open reasoning model to date

Kimi K2.5

Moonshot AI's native multimodal model, delivering state-of-the-art visual coding…

Kimi K2.6

Moonshot AI's next-generation multimodal model, designed for long-horizon coding

Kimi K2.7 Code (batch)

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family

Nous

Hermes 2 Pro - Llama-3 8B

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2

Hermes 3 405B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2

Hermes 3 405B Instruct (free)

Free 405B generalist with agentic skills, roleplay and long-context coherence beyond Hermes 2.

Hermes 3 70B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2

Hermes 4 405B

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous…

Hermes 4 70B

Hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B.

NVIDIA

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA

Nemotron 3 Ultra (free)

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA

Nemotron 3.5 Content Safety (free)

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from…

Llama 3.3 Nemotron Super 49B V1.5

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived…

Llama Nemotron Embed VL 1B V2 (free)

The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering…

Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and…

Nemotron 3 Nano 30B A3B (free)

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and…

Nemotron 3 Nano Omni (free)

Free 30B open multimodal model built as a perception sub-agent inside enterprise agent systems.

Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model

Nemotron 3 Super (free)

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model

Nemotron Nano 12B 2 VL (free)

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for…

Nemotron Nano 9B V2

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA

Nemotron Nano 9B V2 (free)

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA

Llama Nemotron Rerank VL 1B V2 (free)

NVIDIA: Llama Nemotron Rerank VL 1B V2 (free) is available on Rewind.ai.

NVIDIATranscription

Nemotron 3.5 ASR Streaming Multilingual 0.6B

Speech recognition model from NVIDIA.

Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA

Nemotron 3.5 Lightning (free)

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA

Nemotron 3 Embed 1B (free)

NVIDIA: Nemotron 3 Embed 1B (free) is available on Rewind.ai.

Nemotron 3 Ultra (batch)

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA

NVIDIATranscription

Parakeet TDT 0.6B v3

NVIDIA's 600M-parameter multilingual speech-to-text model built on the…

Baidu

CoBuddy (free)

CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows.

ERNIE 4.5 21B A3B

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B…

ERNIE 4.5 21B A3B Thinking

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model

ERNIE 4.5 300B A47B

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu…

ERNIE 4.5 VL 28B A3B

A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B…

ERNIE 4.5 VL 424B A47B

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5…

Qianfan-OCR-Fast (free)

Free multimodal model purpose-built for OCR, keeping general vision skills alongside text.

Gryphe

GrypheChat

MythoMax 13B

One of the most popular Llama 2 13B fine-tunes, tuned for roleplay and rich descriptive prose.

Kling

KlingVideo

Video v3.0 Pro

Kuaishou's premium tier: 3-15 second clips from text or images, with first- and last-frame control.

KlingVideo

Video v3.0 Standard

Kuaishou's standard tier: 3-15 second clips from text or images with first- and last-frame control.

KlingVideo

Video O1

Kling Video O1 is a video generation model from Kuaishou.

AionLabs

Aion-3.0

Multi-model roleplaying and storytelling system from AionLabs

Aion-3.0-Mini

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs

Aion-1.0

Multi-model system designed for high performance across various tasks

Aion-1.0-Mini

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model

Aion-2.0

DeepSeek V3.2 tuned for immersive roleplay, strong at pushing tension and conflict into a story.

Aion-RP 1.0 (8B)

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto…

Venice

VeniceChat

Uncensored

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of…

VeniceChat

Uncensored (free)

Free uncensored instruct-tuned fine-tune of Mistral Small 24B, built by dphn.ai with Venice.ai.

TheDrummer

Cydonia 24B V4.1

Uncensored creative-writing model on Mistral Small 3.2 24B, with good recall and prompt adherence.

Rocinante 12B

Designed for engaging storytelling and rich prose.

Skyfall 36B V2

Enhanced iteration of Mistral Small 2501, specifically fine-tuned for…

UnslopNemo 12B

UnslopNemo v4.1 is the latest addition from the creator of Rocinante

Sao10K

Llama 3 Euryale 70B v2.1

Creative-roleplay model from Sao10k, tuned for prompt adherence and spatial awareness.

Llama 3 8B Lunaris

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3.

Llama 3.1 70B Hanami x1

This is Sao10K's experiment over Euryale v2.2.

Llama 3.1 Euryale 70B v2.2

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k.

Llama 3.3 Euryale 70B

Euryale L3.3 70B is a model focused on creative roleplay from Sao10k.

OpenRouter

Auto Router (Beta)

Task-aware router from OpenRouter.

Fusion

Fusion turns your prompt into a small multi-model deliberation.

Auto Router

"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below)

Body Builder (beta)

Transform your natural language requests into structured OpenRouter API request objects.

Free Models Router

The simplest way to get free inference. openrouter/free is a router that selects free models at…

Owl Alpha

High-performance foundation model designed for agentic workloads.

Pareto Code Router

The Pareto Router is a way to have OpenRouter always pick a strong coding model for your needs…

Mistral

Codestral 2508

Mistral's cutting-edge language model for coding released end of July 2025.

Codestral Embed 2505

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases

Devstral 2 2512

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.

Devstral Medium

High-performance code generation and agentic reasoning model developed…

Devstral Small 1.1

24B parameter open-weight language model for software engineering agents

Ministral 3 14B 2512

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and…

Ministral 3 3B 2512

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful

Ministral 3 8B 2512

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful

Mistral 7B Instruct v0.1

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks

Mistral Embed 2312

Mistral Embed is a specialized embedding model for text data, optimized for semantic search and…

Large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`).

Large 2407

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407).

Large 2411

Mistral Large 2 2411 is an update of Mistral Large 2 released together with Pixtral Large 2411 It…

Mistral Large 3 2512

Mistral’s most capable model to date, featuring a sparse…

Mistral Medium 3

High-performance enterprise-grade language model designed to deliver…

Mistral Medium 3.5

Dense 128B instruction-following model from Mistral AI.

Mistral Medium 3.1

Updated version of Mistral Medium 3, which is a high-performance…

Mistral Nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with…

Saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South…

Mistral Small 3

24B-parameter language model optimized for low-latency performance across…

Mistral Small 4

Next major release in the Mistral Small family

Mistral Small 3.1 24B

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501)

Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for…

Mixtral 8x22B Instruct

Mistral's official instruct fine-tuned version of Mixtral 8x22B.

Pixtral Large 2411

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2.

Voxtral Mini TTS

Mistral's text-to-speech model featuring zero-shot voice cloning and…

Voxtral Small 24B 2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input…

Ministral 8B

8B parameter model featuring a unique interleaved sliding-window attention…

MistralTranscription

Voxtral Mini 3B 2507

Speech and audio understanding model from Mistral AI.

MistralTranscription

Voxtral Mini Transcribe

Mistral's speech-to-text model, derived from the Voxtral Mini family.

MistralTranscription

Voxtral Small 24B 2507 STT

Speech transcription model from Mistral AI.

Kwaipilot

KwaipilotChat

KAT-Coder-Air V2.5

Flagship-level Agentic Coding model that can directly hand over an entire…

KwaipilotChat

KAT-Coder-Pro V2.5

Flagship-level Agentic Coding model that can directly hand over an entire…

KwaipilotChat

KAT-Coder-Pro V2

Latest high-performance model in KwaiKAT’s KAT-Coder series

inclusionAI

Ring-2.6-1T

1T-parameter-scale thinking model with 63B active parameters

Ling-2.6-1T

Instant (instruct) model from inclusionAI and the company’s trillion-parameter…

Ling-2.6-flash

Instant (instruct) model from inclusionAI with 104B total parameters and 7.4B…

Ring-2.6-1T (free)

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters

Ling-3.0-flash

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*

Ling-3.0-flash (free)

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*

TNG

TNGChat

DeepSeek R1T2 Chimera

671B MoE assembled from DeepSeek R1-0528, R1 and V3-0324 by TNG's Assembly-of-Experts method.

Cohere

North Mini Code (free)

North Mini Code is Cohere's first agentic coding model and the debut of its North family.

Command A

Open-weights 111B parameter model with a 256k context window focused on delivering…

Command R (08-2024)

command-r-08-2024 is an update of the Command R with improved performance for multilingual…

Command R+ (08-2024)

command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25%…

Command R7B (12-2024)

Small, fast update of the Command R+ model, delivered in December 2024.

Rerank 4 Fast

Cohere's AI search foundation model for enhancing the relevance of information surfaced within…

Rerank 4 Pro

Cohere's AI search foundation model for enhancing the relevance of information surfaced within…

Rerank v3.5

Designed to reorder search results for improved relevance.

Microsoft

MicrosoftChat

Phi 4

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate…

MicrosoftChat

Phi 4 Mini Instruct

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly…

MicrosoftChat

WizardLM-2 8x22B

Microsoft AI's most advanced Wizard model.

MicrosoftImage

MAI-Image-2.5

Microsoft's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry.

MicrosoftImage

MAI-Image-2.5 Pro

Microsoft's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry.

MicrosoftTranscription

MAI-Transcribe 1.5

Multilingual speech-to-text model from Microsoft AI.

MicrosoftSpeech

MAI-Voice-2

Expressive text-to-speech model from Microsoft.

MicrosoftSpeech

MAI-Voice-2-Flash

Low-latency text-to-speech model from Microsoft for voice agents

Poolside

Laguna M.1

Flagship coding agent model from Poolside, optimized for complex software…

Laguna XS 2.1

Latest coding agent model in the 33B-A3B category from Poolside and a step…

Laguna XS 2.1 (free)

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step…

Laguna M.1 (free)

Laguna M.1 is the flagship coding agent model from Poolside, optimized for complex software…

Laguna XS.2 (free)

Laguna XS.2 is the second-generation model in the XS size class from Poolside

Laguna S 2.1

Latest coding agent model from Poolside.

Laguna S 2.1 (free)

Laguna S 2.1 is the latest coding agent model from Poolside.

BAAI

BAAIChat

bge-base-en-v1.5

The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into…

BAAIChat

bge-large-en-v1.5

The bge-large-en-v1.5 embedding model maps English sentences, paragraphs and documents into a…

BAAIChat

bge-m3

The bge-m3 embedding model encodes sentences, paragraphs and long documents into a…

Amazon

Nova 2 Lite

Fast, cost-effective reasoning model for everyday workloads that can process…

Nova Lite 1.0

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast…

Nova Micro 1.0

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the…

Nova Premier 1.0

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks…

Nova Pro 1.0

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination…

Arcee AI

Coder Large

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on…

Maestro Reasoning

Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B…

Spotlight

7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned…

Trinity Large Preview

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee

Trinity Large Thinking

Powerful open source reasoning model from the team at Arcee AI.

Trinity Mini

26B-parameter (3B active) sparse mixture-of-experts language model featuring 128…

Virtuoso Large

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters

LiquidAI

LFM2-24B-A2B

Largest model in the LFM2 family of hybrid architectures designed for…

LFM2.5-1.2B-Instruct (free)

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast…

LFM2.5-1.2B-Thinking (free)

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks

LFM2.5-2.6B (free)

LFM2.5-2.6B is a compact reasoning model from Liquid AI.

AI21

AI21Chat

Jamba Large 1.7

Latest model in the Jamba open family, offering improvements in grounding

IBM

IBMChat

Granite 4.0 Micro

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models.

IBMChat

Granite 4.1 8B

Dense, decoder-only 8-billion-parameter language model from IBM

Perplexity

Embed V1 0.6B

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for…

Embed V1 4B

pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for…

Sonar

Lightweight, affordable, fast and simple to use - now featuring citations and the ability…

Sonar Deep Research

Research-focused model designed for multi-step retrieval

Sonar Pro

Note: Sonar Pro pricing includes Perplexity search pricing.

Sonar Pro Search

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most…

Sonar Reasoning Pro

Note: Sonar Pro pricing includes Perplexity search pricing.

Recraft

Recraft V3

Image generation model from Recraft.

Recraft V4

Image generation model from Recraft.

Recraft V4 Pro

Image generation model from Recraft.

Recraft V4.1

Image generation model from Recraft tuned for high aesthetics.

Recraft V4.1 Pro

Image generation model from Recraft tuned for high aesthetics.

Recraft V4.1 Pro Vector

Vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics.

Recraft V4.1 Utility

General-purpose image generation model from Recraft.

Recraft V4.1 Utility Pro

General-purpose image generation model from Recraft.

Recraft V4.1 Vector

Vector (SVG) variant of Recraft V4.1, tuned for high aesthetics.

Recraft V4 Pro Vector

Vector (SVG) variant of Recraft V4 Pro.

Anthracite-Org

Anthracite-OrgChat

Magnum v4 72B

This is a series of models designed to replicate the prose quality of the Claude 3 models

Nex AGI

Nex AGIChat

Nex-N2-Mini

Open-source agentic mixture-of-experts model from Nex AGI

Nex AGIChat

Nex-N2-Pro

Agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of…

Nex AGIChat

DeepSeek V3.1 Nex N1

DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series - a post-trained model designed…

Rekaai

RekaaiChat

Edge

Extremely efficient 7B multimodal vision-language model that accepts…

RekaaiChat

Flash 3

General-purpose, instruction-tuned large language model with 21 billion…

hexgrad

hexgradSpeech

Kokoro 82M

Lightweight, open-weight text-to-speech model.

Sesame

SesameChat

CSM 1B

Conversational speech model from Sesame.

Inception

InceptionChat

Mercury 2

Extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).

Morph

MorphChat

Morph V3 Fast

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code…

MorphChat

Morph V3 Large

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for…

StepFun

StepFunChat

Step 3.7 Flash

StepFun's latest high-efficiency multimodal Mixture-of-Experts model.

StepFunChat

Step 3.5 Flash

StepFun's most capable open-source foundation model.

AlfredPros

AlfredProsChat

CodeLLaMa 7B Instruct Solidity

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract…

AllenAI

AllenAIChat

Olmo 3 32B Think

Large-scale, 32-billion-parameter model purpose-built for deep reasoning

Intfloat

IntfloatChat

E5-Base-v2

The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional…

IntfloatChat

E5-Large-v2

The e5-large-v2 embedding model maps English sentences, paragraphs and documents into a…

IntfloatChat

Multilingual-E5-Large

The multilingual-e5-large embedding model encodes sentences, paragraphs and documents across over…

Mancer

MancerChat

Weaver (alpha)

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or…

Upstage

UpstageChat

Solar Pro 3

Upstage's powerful Mixture-of-Experts (MoE) language model.

UpstageChat

Solar Pro 4

Upstage's cost-efficient large language model, featuring a 524K context window.

Zyphra

ZyphraChat

Zonos v0.1 Hybrid

Text-to-speech model from Zyphra built on a hybrid architecture.

ZyphraChat

Zonos v0.1 Transformer

Text-to-speech model from Zyphra built on a pure transformer…

Alpindale

AlpindaleChat

Goliath 120B

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model.

Canopy Labs

Canopy LabsChat

Orpheus 3B

English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and…

Deep Cogito

Deep CogitoChat

Cogito v2.1 671B

Cogito v2.1 671B MoE represents one of the strongest open models globally

Deepgram

DeepgramSpeech

Aura-2

Multilingual text-to-speech model from Deepgram.

DeepgramSpeech

Flux TTS (free)

Flux TTS is a text-to-speech model from Deepgram.

DeepgramTranscription

Nova-3

Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual…

Dots Studio

Dots StudioChat

Dots3-Note Preview (free)

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio

EssentialAI

EssentialAIChat

Rnj 1 Instruct

Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained…

Fish Audio

S1

S1 is a multilingual text-to-speech model from Fish Audio.

S2.1 Pro

S2.1 Pro is a production-oriented text-to-speech model from Fish Audio.

S2.1 Pro Free (free)

S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for testing, prototyping

S2 Pro

S2 Pro is a multilingual text-to-speech model from Fish Audio.

Fish AudioTranscription

Transcribe 1

Transcribe 1 is a speech-to-text model from Fish Audio.

Inflection

InflectionChat

Inflection 3 Pi

Inflection 3 Pi powers Inflection's Pi chatbot, including backstory, emotional intelligence

InflectionChat

Krea

KreaImage

Krea 2 Large

Krea's high-capability image generation model, more than twice the size of Krea 2…

KreaImage

Krea 2 Medium

Krea's balanced, cost-efficient image generation model and a practical starting…

KreaImage

Krea 2 Medium Turbo

Distilled, speed-focused variant of Krea 2 Medium from Krea.

Meituan

MeituanChat

LongCat 2.0

Sparse mixture-of-experts language model from Meituan

Perceptron

PerceptronChat

Perceptron Mk1

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and…

Prime Intellect

Prime IntellectChat

INTELLECT-3

106B-parameter Mixture-of-Experts model (12B active) post-trained from…

Relace

RelaceChat

Relace Apply 3

Specialized code-patching LLM that merges AI-suggested edits straight into…

RelaceChat

Relace Search

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase…

Runway

RunwayVideo

Aleph 2.0

Runway Aleph 2.0 is an in-context video editing model from Runway.

RunwayVideo

Gen-4.5

Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video…

Sakana

SakanaChat

Fugu Ultra

Higher-performance model in Sakana AI's Fugu family.

SakanaChat

Sakana Namazu

Japanese-specialized reasoning model from Sakana AI

Sentence Transformers

all-MiniLM-L12-v2

The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional…

all-MiniLM-L6-v2

The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional…

all-mpnet-base-v2

The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a…

multi-qa-mpnet-base-dot-v1

Embedding model for semantic search: turns sentences and short passages into vectors.

paraphrase-MiniLM-L6-v2

The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a…

SpaceXAI

SpaceXAIChat

Grok 4.6

SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

SpaceXAIImage

Grok Imagine Image Quality

SpaceXAI's fast, high-fidelity image generation and editing model.

SpaceXAIVideo

Grok Imagine Video

SpaceXAI's fast, text-, image-, and reference-conditioned video generation…

SpaceXAIVideo

Grok Imagine Video 1.5

Video generation model from SpaceXAI.

SpaceXAITranscription

Grok STT 1.0

Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint.

SpaceXAISpeech

stealth

stealthChat

Ox Alpha

Reasoning model designed for coding, sustained agentic work, and production workloads.

Switchpoint

SwitchpointChat

Router

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an…

Thenlper

ThenlperChat

GTE-Base

Compact English embedding model producing 768-dimensional vectors for search and similarity.

ThenlperChat

GTE-Large

Larger English embedding model for sentences, paragraphs and moderate-length documents.

Thinking Machines

Inkling

Open-weight multimodal mixture-of-experts model from Thinking Machines Lab

Inkling (batch)

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab

Inkling (free)

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab

Inkling Small

Open-weight multimodal mixture-of-experts model from Thinking Machines Lab

Inkling Small (free)

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab

Undi95

Undi95Chat

ReMM SLERP 13B

A recreation trial of the original MythoMax-L2-B13 but with updated models.

VoyageAI by MongoDB

rerank-2.5

VoyageAI by MongoDB: rerank-2.5 is available on Rewind.ai.

rerank-2.5-lite

VoyageAI by MongoDB: rerank-2.5-lite is available on Rewind.ai.

voyage-4

VoyageAI by MongoDB: voyage-4 is available on Rewind.ai.

voyage-4-large

VoyageAI by MongoDB: voyage-4-large is available on Rewind.ai.

voyage-4-lite

VoyageAI by MongoDB: voyage-4-lite is available on Rewind.ai.